Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/dimknaf/braindb/claude-mdgit clone --depth 1 https://github.com/dimknaf/braindbWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02750 | $0.02750 |
| Opus 5 | $0.01375 | $0.01375 |
| Sonnet 5 | $0.00550 | $0.00550 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade A, and why
braindb CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8000/api/v1/memory/rules How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BrainDB — Claude Instructions
This project is a memory database and REST API designed to be driven by you (Claude) via HTTP calls. The API runs at http://localhost:8000.
⚠ TOOL PRIORITY — read this first, it overrides habit
BrainDB's entire value is the graph + embeddings + ranking. Recall and
understanding must go through the sophisticated retrieval, never a flat SQL
SELECT.
POST /api/v1/memory/context(multi-query) — the default for ALL recall, discovery, disambiguation, "what do we know about X". BOTH the fuzzy and the embedding pathways are keyword-mediated: the query is matched against keyword-entity content (via pg_trgm) and keyword embeddings, then entities surface viatagged_with. A two-level diversity quota (per-search-term + per-keyword, geometric decay) keeps results balanced + graph traversal + temporal decay +final_rank.POST /api/v1/agent/query(ask it to delegate to a subagent for anything multi-step) — research/investigation that needs several hops.GET /api/v1/entities…,/memory/tree/<id>,/entities/<id>/relations— targeted structure lookups.POST /api/v1/memory/sql— exception ONLY. A flat SELECT throws away embeddings, graph and ranking. Use it solely for a specific structured/aggregate question (counts, GROUP BY, activity-log joins) the above genuinely cannot express. Never for recall, discovery, similarity, or understanding. If you're using SQL to find or understand something, you're doing it wrong — use/memory/context.
Previews vs full read: all multi-item calls return short previews
(~1K/item; a clipped one ends --truncated … get_entity("<id>")). Read a
full body only by id: GET /api/v1/entities/{id}. For a large body, page it
with ?offset=&limit= (follow content_meta.next_offset) or delegate it to a
subagent — never pull whole documents into context.
At the Start of Every Session
Before doing any work, consult your memory:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 201 lines · 2,750 tokens per session scan A 0d42d57b1adf
braindb CLAUDE.md is an instructions file published in the GitHub repository dimknaf/braindb (107 stars, last pushed 12d ago), licensed Apache-2.0. It adds 2,750 tokens to every session, about $0.0137 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agentscope copilot-instructions.md
Copilot instructions for agentscope-ai/agentscope, covering agentscope code review guide, 1. code quality, 2. [must] code security, 3. [must] testing & dependencies and 4. code standards.
obsidian-llm-wiki AGENTS.md
Instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
obsidian-llm-wiki CLAUDE.md
Instructions for green-dalii/obsidian-llm-wiki, a project described as: Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
DM-Code-Agent AGENTS.md
Instructions for hwfengcs/DM-Code-Agent, covering agents.md, project intent, development rules, verification and important modules.
OmicsClaw AGENTS.md
Instructions for TianGzlab/OmicsClaw, covering agents.md — omicsclaw guide for ai coding agents, repository working contract, project overview, setup and pip install -e .
OmicsClaw CLAUDE.md
Instructions for TianGzlab/OmicsClaw, covering claude.md — omicsclaw agent instructions, repository maintenance contract, agent skills, issue tracker and triage labels.